Move document context and identifiers in document.rs

This commit is contained in:
ManyTheFish
2025-06-30 14:21:46 +02:00
parent 6b2b8ed676
commit 7a204609fe
16 changed files with 182 additions and 169 deletions

View File

@@ -8,10 +8,10 @@ use super::DelAddRoaringBitmap;
use crate::constants::RESERVED_GEO_FIELD_NAME;
use crate::update::new::channel::{DocumentsSender, ExtractorBbqueueSender};
use crate::update::new::document::{write_to_obkv, Document};
use crate::update::new::document_change::DatabaseDocument;
use crate::update::new::indexer::document_changes::{DocumentContext, Extractor, IndexingContext};
use crate::update::new::document::{DocumentContext, DocumentIdentifiers};
use crate::update::new::indexer::document_changes::{Extractor, IndexingContext};
use crate::update::new::indexer::settings_changes::{
settings_change_extract, DatabaseDocuments, SettingsChangeExtractor,
settings_change_extract, DocumentsIndentifiers, SettingsChangeExtractor,
};
use crate::update::new::ref_cell_ext::RefCellExt as _;
use crate::update::new::thread_local::{FullySend, ThreadLocal};
@@ -194,7 +194,7 @@ impl<'extractor> SettingsChangeExtractor<'extractor> for SettingsChangeDocumentE
fn process<'doc>(
&self,
documents: impl Iterator<Item = Result<DatabaseDocument<'doc>>>,
documents: impl Iterator<Item = Result<DocumentIdentifiers<'doc>>>,
context: &DocumentContext<Self::Data>,
) -> Result<()> {
let mut document_buffer = bumpalo::collections::Vec::new_in(&context.doc_alloc);
@@ -242,7 +242,7 @@ impl<'extractor> SettingsChangeExtractor<'extractor> for SettingsChangeDocumentE
/// and then updates the database.
#[tracing::instrument(level = "trace", skip_all, target = "indexing::documents::extract")]
pub fn update_database_documents<'indexer, 'extractor, MSP, SD>(
documents: &'indexer DatabaseDocuments<'indexer>,
documents: &'indexer DocumentsIndentifiers<'indexer>,
indexing_context: IndexingContext<MSP>,
extractor_sender: &ExtractorBbqueueSender,
settings_delta: &SD,

View File

@@ -15,9 +15,10 @@ use crate::filterable_attributes_rules::match_faceted_field;
use crate::heed_codec::facet::OrderedF64Codec;
use crate::update::del_add::DelAdd;
use crate::update::new::channel::FieldIdDocidFacetSender;
use crate::update::new::document::DocumentContext;
use crate::update::new::extract::perm_json_p;
use crate::update::new::indexer::document_changes::{
extract, DocumentContext, DocumentChanges, Extractor, IndexingContext,
extract, DocumentChanges, Extractor, IndexingContext,
};
use crate::update::new::ref_cell_ext::RefCellExt as _;
use crate::update::new::steps::IndexingStep;

View File

@@ -10,8 +10,8 @@ use serde_json::value::RawValue;
use serde_json::Value;
use crate::error::GeoError;
use crate::update::new::document::Document;
use crate::update::new::indexer::document_changes::{DocumentContext, Extractor};
use crate::update::new::document::{Document, DocumentContext};
use crate::update::new::indexer::document_changes::Extractor;
use crate::update::new::ref_cell_ext::RefCellExt as _;
use crate::update::new::thread_local::MostlySend;
use crate::update::new::DocumentChange;

View File

@@ -8,10 +8,11 @@ use bumpalo::Bump;
use super::match_searchable_field;
use super::tokenize_document::{tokenizer_builder, DocumentTokenizer};
use crate::update::new::document::DocumentContext;
use crate::update::new::extract::cache::BalancedCaches;
use crate::update::new::extract::perm_json_p::contained_in;
use crate::update::new::indexer::document_changes::{
extract, DocumentContext, DocumentChanges, Extractor, IndexingContext,
extract, DocumentChanges, Extractor, IndexingContext,
};
use crate::update::new::ref_cell_ext::RefCellExt as _;
use crate::update::new::steps::IndexingStep;

View File

@@ -7,10 +7,10 @@ use bumpalo::Bump;
use super::match_searchable_field;
use super::tokenize_document::{tokenizer_builder, DocumentTokenizer};
use crate::proximity::{index_proximity, MAX_DISTANCE};
use crate::update::new::document::Document;
use crate::update::new::document::{Document, DocumentContext};
use crate::update::new::extract::cache::BalancedCaches;
use crate::update::new::indexer::document_changes::{
extract, DocumentContext, DocumentChanges, Extractor, IndexingContext,
extract, DocumentChanges, Extractor, IndexingContext,
};
use crate::update::new::ref_cell_ext::RefCellExt as _;
use crate::update::new::steps::IndexingStep;

View File

@@ -10,8 +10,8 @@ use crate::error::FaultSource;
use crate::progress::EmbedderStats;
use crate::prompt::Prompt;
use crate::update::new::channel::EmbeddingSender;
use crate::update::new::document_change::DatabaseDocument;
use crate::update::new::indexer::document_changes::{DocumentContext, Extractor};
use crate::update::new::document::{DocumentContext, DocumentIdentifiers};
use crate::update::new::indexer::document_changes::Extractor;
use crate::update::new::indexer::settings_changes::SettingsChangeExtractor;
use crate::update::new::thread_local::MostlySend;
use crate::update::new::vector_document::VectorDocument;
@@ -343,7 +343,7 @@ impl<'extractor> SettingsChangeExtractor<'extractor> for SettingsChangeEmbedding
fn process<'doc>(
&'doc self,
documents: impl Iterator<Item = crate::Result<DatabaseDocument<'doc>>>,
documents: impl Iterator<Item = crate::Result<DocumentIdentifiers<'doc>>>,
context: &'doc DocumentContext<Self::Data>,
) -> crate::Result<()> {
let embedders = self.embedders.inner_as_ref();